Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Navigation Visual Question Answering on NaVQA Medium (M) horizon
Loading...
73.7
Descriptive Accuracy
ReMEmbR
41.148
49.599
58.05
66.501
Jun 23, 2026
Descriptive Accuracy
Positional Error (m)
Temporal Error (min)
Updated 1mo ago
Evaluation Results
Method
Method
Links
Descriptive Accuracy
Positional Error (m)
Temporal Error (min)
ReMEmbR
LLM=Gemini-3-Pro, Enco...
2026.06
73.7
24.52
1.08
ReMEmbR
LLM=Gemini-2.5-Flash,...
2026.06
60.5
28.89
2.01
RAVEN
LLM=Gemini-2.5-Pro, En...
2026.06
60.5
12.29
0.69
VLM Only
LLM=Gemini-2.5-Pro
2026.06
60.5
12.35
0.98
VLM Only
LLM=Gemini-2.5-Flash
2026.06
50
12.48
1.19
RAVEN
LLM=Gemini-2.5-Flash,...
2026.06
47.4
16.2
0.67
RAVEN
LLM=Gemini-2.5-Flash,...
2026.06
42.4
60.51
1.4
Feedback
Search any
task
Search any
task